Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2515. Min Act: -0.0000

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2536. Min Act: -0.0000

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2339. Min Act: -0.0000

Data Index: 591479 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2411. Min Act: -0.0000

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2156. Min Act: -0.0000

Data Index: 459483 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2308. Min Act: -0.0000

Data Index: 703651 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1137117 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2044. Min Act: -0.0000

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2087. Min Act: -0.0001

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2262. Min Act: -0.0000

Data Index: 369919 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1973. Min Act: -0.0000

Data Index: 13728 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1140897 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2137. Min Act: -0.0000

Data Index: 55831 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2329. Min Act: -0.0000

Data Index: 738037 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2177. Min Act: -0.0001

Data Index: 445173 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1301335 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2079. Min Act: -0.0000

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 798